Parallel Clique Optimization on GPUs
01Research under Dr. Vishwesh Jatala2023 - Present
Scroll to explore
Researchfocusedonacceleratingmaximalcliquefindinginlarge-scalegraphsthroughnovelGPU-basedparallelizationstrategies,significantlyoptimizingcomputationalcomplexityfordensegraphstructures.
Redesigned traditional clique optimization algorithms for massive parallel execution on CUDA-enabled GPUs.
Introduced optimized thread-block mapping strategies to reduce warp divergence and memory bottlenecks.
Implemented shared memory utilization techniques for efficient neighborhood intersection computation.
Benchmarked performance improvements against CPU-based and baseline GPU implementations.
Work in detail
01 // Exhibit
GPU PARALLELIZATION
Optimized thread scheduling and memory coalescing for large nodal graph clique minimization.
A closer look
Next in the archive
